基于Copula相关结构的企业供应链融资风险度量
|
摘要
近年来，企业融资难问题一直是阻碍我国经济发展的主要因素之一，政府出台很多政策和措施去解决这一难题，然而实际效用还有待提高。造成企业融资难的主要原因就是融资资质不足，融资风险难以度量，融资后因其违约成本较低导致违约风险较高，对其监管较难。依托供应链金融业务的供应链融资为解决企业融资难提供可能。供应链金融业务使资金流和货物流在供应链内产生局部闭合性，尤其是中小企业处于供应链的上下游重要环节上，与供应链核心企业之间形成紧密的伴生关系，核心企业的良好经营状况和信用资质，能通过供应链金融的整体性有效地传导给企业。
在供应链融资中，企业融资后发生违约的可能较低，因为银行通过对供应链上物权和账款的监管，可直接了解融资企业的经营动态，有效防范和规避企业供应链融资违约。对银行来说供应链融资风险管理主要在企业供应链融资前的风险评估阶段，客观准确的风险度量可使银行有效规避企业供应链融资违约的发生。因此，在满足企业融资需求的同时，结合供应链融资的实际业务特点，为银行提供有一种全新的供应链融资风险度量方法和风险监控体系成为理论研究亟需解决的实际问题。
目前国内的研究主要集中于供应链融资的运营模式、管理方式和风险种类的相关理论研究，对基于供应链金融的企业供应链融资中所蕴含的风险度量问题关注较少。在融资风险管理中较多运用定性分析方法，综述性的分析风险的种类、特性的文献较多，缺少直观的评估风险方式和量化模型；在供应链融资风险度量方面，主要以融资企业的角度出发，度量单一企业的融资违约风险，较少以银行等金融机构的角度评估供应链融资整体的风险性，整体性是供应链融资的最大特点。
因此，论文以供应链的整体性为基点建立企业供应链融资风险度量模型，为银行构建供应链融资风险预警系统和风险监控体系是其研究的主要结论。论文各章的概况如下：
第一章阐明选题的概况，包括：研究的背景、研究的目的和意义、研究的现状、研究内容和创新点等。第二章对企业供应链融资风险的理论基础进行梳理，为研究的主体部分做理论铺垫。
第三章构建供应链融资企业间的相关结构。由于企业供应链融资风险具有相依性，Copula结构可以度量这种风险的相依性，进而可以度量供应链融资整体违约风险。研究中选取阿基米德Copula函数来度量供应链上企业的整体相关性，建立企业间的Copula相关结构。
第四章运用信息熵法对企业的财务风险状况进行评估，得到企业财务状况得分的概率分布，进而得到财务风险违约的概率值。基于Copula相依结构计算出企业供应链融资的整体财务风险违约概率值。
第五章利用GARCH-M模型，估计出企业收益率的波动率，然后利用KMV模型计算出企业的信用违约距离，利用修正的KMV模型我们计算出企业发生信用违约风险的概率，基于Copula相依结构度量企业供应链融资的整体信用违约风险概率值。
第六章利用结构方程（SEM）的验证性因素分析（CFA），对财务风险的结构模型进行检验，通过模型输出的因素负荷量，得出指标变量对潜在变量的解释能力。再利用二阶验证性因素分析，得出一阶潜在变量对财务风险的解释能力、潜在变量间的相依程度以及模型整体的组合效度。
第七章建立风险预警系统。采用循环修正的组合评价方法对企业供应链融资的财务风险和信用风险的排名结果进行修正，得出企业供应链融资风险排名，构建风险等级色彩预警系统。利用验证性因素分析结论建立企业供应链融资风险识别指标体系。
研究的主要结果：1.构建企业间多元阿基米德Copula相依结构；2.结合信息熵和Copula结构度量供应链融资的财务风险；3.用GARCH-M模型估计企业收益的波动率，结合KMV模型和Copula结构度量供应链融资的信用风险；4.利用结构方程理论分析供应链融资违约的影响因素；5.用循环修正的组合评价方法对供应链融资风险的度量结果进行循环修正。根据上述研究结果构建供应链融资风险预警系统和供应链融资风险监控系统。
In recent years, financing difficulties of enterprises has always been one of mainfactors hindering the economic development of China. And the government introducedmany policies and measures, trying to solve these problems, but the effect is still to beimproved. The root of them lies in the lack of financing credit qualification, high defaultprobability resulted from low default cost, and tough supervision and management.However, with the development and innovation of supply chain finance business, supplychain financing makes it possible to solve the problems. The most striking feature ofsupply chain lies in the closed property of enterprise finance on supply chain, namely thepartial closure derived from capital and goods flow within the supply chain. The smalland medium-sized enterprises occupy an crucial position in the upstream anddownstream of the supply chain, forming a close symbiotic relationship with coreenterprises, whose good operating performance and creditworthiness will be efficientlypassed on to them through the integrity of supply chain.
In the supply chain financing, the financing default probability is low, in that bysupervising and managing the real rights and accounts, the bank can directly get businessdynamic information and effectively guard against and even evade the defaults. ForBanks the risk management is mainly focus on evaluating the risk before financing, so anobjective and accurate risk measurement can make the bank effectively evade financingdefaults. Therefore, to satisfy the needs of enterprises, meantime, considering thebusiness features of supply chain financing, providing a brand-new risk measurement andmonitoring system becomes a priority.
Most people in domestic focus more on the operation, management and theories ofrisk types of supply chain and pay less attention on risk measuring. And more qualitativeanalysis methods, more summarily analyzing the types and features of risk， lessintuitively assessing methods and quantitative model; In terms of supply chain financingrisk measurement, more from the perspective of financing enterprises, measuringsingle-enterprise financing default risk, less from the perspective of financial institutionsto assess the risk of the whole supply chain, ignoring the integrity of the supply chainfinancing. However, the integrity is the most striking feature.
Therefore, based on the integrity, we set up financing risk measurement model, andbuild warning and monitoring system of supply chain financing risk for banks, which isthe main research conclusions. The chapters’ overview is as follows:
In chapter1we expound the topics, including the background, the present situation,purpose, content, significance and innovative points, and some others. In chapter2wearrange the basic theory of supply chain financing risk, preparing for the followingresearch.
In chapter3we construct the relational structure among the enterprises.Archimedes’ copula function is used in our research to estimate the pertinence and thenconstruct the relational structure among the enterprises, in that the pertinence ofenterprise’s financing risk has dependency with each other, and the copula function canestimate it and then apply the results to the whole supply chain.
In chapter4we evaluate the financial risk of the enterprises through informationentropy method, find the distribution probability of enterprises’ scores, and analyze theprobability of financial default risk. Then copula relational structure is constructed tocalculate the probability of financial risk of the supply chain.
In chapter5we estimate the volatility of enterprise profitability by GARCH-Mmodel and calculate the credit default distance of enterprise by KMV model. Throughmodified KMV model we calculate the occurrence rate of credit default. Then we can usecopula connect dependent structure to measure the market default probability in thesupply chain.
In chapter6by the confirmatory factor analysis (CFA) of the structural equation(SEM) we check the structural model of financial risk and get out to what extentindicator variables can explain the potential variables through factor loading from ourmodel. By second-order CFA, we find out to what extent the first-order potentialvariables will affect the financial risk and to what degree the potential variables dependon each other and the validity of the combination of the whole model.
In chapter7we build up risk warning system, correct the ranking results of financialand credit risk of enterprise financing by circularly revised combination evaluation model,and get the ranking results of enterprise financing risk based on supply chain, then wecan build up colored risk level warning. Finally by CFA we build up enterprise financing risk indicator identifying system.
Our main innovation:1. construct the relational structure among the enterprises byArchimedes copula function;2. measure the financing risk of the supply chain financingby the information entropy and copula connect structure;3. estimate earnings volatilityby GARCH-M model, combine KMV model and copulas connect structure to measurecredit risk of supply chain financing;4. analyze the influence factors of supply chainfinancing by SEM theory5. constantly correct the results of supply chain financing bycircularly revised combination evaluation model.
在供应链融资中，企业融资后发生违约的可能较低，因为银行通过对供应链上物权和账款的监管，可直接了解融资企业的经营动态，有效防范和规避企业供应链融资违约。对银行来说供应链融资风险管理主要在企业供应链融资前的风险评估阶段，客观准确的风险度量可使银行有效规避企业供应链融资违约的发生。因此，在满足企业融资需求的同时，结合供应链融资的实际业务特点，为银行提供有一种全新的供应链融资风险度量方法和风险监控体系成为理论研究亟需解决的实际问题。
目前国内的研究主要集中于供应链融资的运营模式、管理方式和风险种类的相关理论研究，对基于供应链金融的企业供应链融资中所蕴含的风险度量问题关注较少。在融资风险管理中较多运用定性分析方法，综述性的分析风险的种类、特性的文献较多，缺少直观的评估风险方式和量化模型；在供应链融资风险度量方面，主要以融资企业的角度出发，度量单一企业的融资违约风险，较少以银行等金融机构的角度评估供应链融资整体的风险性，整体性是供应链融资的最大特点。
因此，论文以供应链的整体性为基点建立企业供应链融资风险度量模型，为银行构建供应链融资风险预警系统和风险监控体系是其研究的主要结论。论文各章的概况如下：
第一章阐明选题的概况，包括：研究的背景、研究的目的和意义、研究的现状、研究内容和创新点等。第二章对企业供应链融资风险的理论基础进行梳理，为研究的主体部分做理论铺垫。
第三章构建供应链融资企业间的相关结构。由于企业供应链融资风险具有相依性，Copula结构可以度量这种风险的相依性，进而可以度量供应链融资整体违约风险。研究中选取阿基米德Copula函数来度量供应链上企业的整体相关性，建立企业间的Copula相关结构。
第四章运用信息熵法对企业的财务风险状况进行评估，得到企业财务状况得分的概率分布，进而得到财务风险违约的概率值。基于Copula相依结构计算出企业供应链融资的整体财务风险违约概率值。
第五章利用GARCH-M模型，估计出企业收益率的波动率，然后利用KMV模型计算出企业的信用违约距离，利用修正的KMV模型我们计算出企业发生信用违约风险的概率，基于Copula相依结构度量企业供应链融资的整体信用违约风险概率值。
第六章利用结构方程（SEM）的验证性因素分析（CFA），对财务风险的结构模型进行检验，通过模型输出的因素负荷量，得出指标变量对潜在变量的解释能力。再利用二阶验证性因素分析，得出一阶潜在变量对财务风险的解释能力、潜在变量间的相依程度以及模型整体的组合效度。
第七章建立风险预警系统。采用循环修正的组合评价方法对企业供应链融资的财务风险和信用风险的排名结果进行修正，得出企业供应链融资风险排名，构建风险等级色彩预警系统。利用验证性因素分析结论建立企业供应链融资风险识别指标体系。
研究的主要结果：1.构建企业间多元阿基米德Copula相依结构；2.结合信息熵和Copula结构度量供应链融资的财务风险；3.用GARCH-M模型估计企业收益的波动率，结合KMV模型和Copula结构度量供应链融资的信用风险；4.利用结构方程理论分析供应链融资违约的影响因素；5.用循环修正的组合评价方法对供应链融资风险的度量结果进行循环修正。根据上述研究结果构建供应链融资风险预警系统和供应链融资风险监控系统。
In recent years, financing difficulties of enterprises has always been one of mainfactors hindering the economic development of China. And the government introducedmany policies and measures, trying to solve these problems, but the effect is still to beimproved. The root of them lies in the lack of financing credit qualification, high defaultprobability resulted from low default cost, and tough supervision and management.However, with the development and innovation of supply chain finance business, supplychain financing makes it possible to solve the problems. The most striking feature ofsupply chain lies in the closed property of enterprise finance on supply chain, namely thepartial closure derived from capital and goods flow within the supply chain. The smalland medium-sized enterprises occupy an crucial position in the upstream anddownstream of the supply chain, forming a close symbiotic relationship with coreenterprises, whose good operating performance and creditworthiness will be efficientlypassed on to them through the integrity of supply chain.
In the supply chain financing, the financing default probability is low, in that bysupervising and managing the real rights and accounts, the bank can directly get businessdynamic information and effectively guard against and even evade the defaults. ForBanks the risk management is mainly focus on evaluating the risk before financing, so anobjective and accurate risk measurement can make the bank effectively evade financingdefaults. Therefore, to satisfy the needs of enterprises, meantime, considering thebusiness features of supply chain financing, providing a brand-new risk measurement andmonitoring system becomes a priority.
Most people in domestic focus more on the operation, management and theories ofrisk types of supply chain and pay less attention on risk measuring. And more qualitativeanalysis methods, more summarily analyzing the types and features of risk， lessintuitively assessing methods and quantitative model; In terms of supply chain financingrisk measurement, more from the perspective of financing enterprises, measuringsingle-enterprise financing default risk, less from the perspective of financial institutionsto assess the risk of the whole supply chain, ignoring the integrity of the supply chainfinancing. However, the integrity is the most striking feature.
Therefore, based on the integrity, we set up financing risk measurement model, andbuild warning and monitoring system of supply chain financing risk for banks, which isthe main research conclusions. The chapters’ overview is as follows:
In chapter1we expound the topics, including the background, the present situation,purpose, content, significance and innovative points, and some others. In chapter2wearrange the basic theory of supply chain financing risk, preparing for the followingresearch.
In chapter3we construct the relational structure among the enterprises.Archimedes’ copula function is used in our research to estimate the pertinence and thenconstruct the relational structure among the enterprises, in that the pertinence ofenterprise’s financing risk has dependency with each other, and the copula function canestimate it and then apply the results to the whole supply chain.
In chapter4we evaluate the financial risk of the enterprises through informationentropy method, find the distribution probability of enterprises’ scores, and analyze theprobability of financial default risk. Then copula relational structure is constructed tocalculate the probability of financial risk of the supply chain.
In chapter5we estimate the volatility of enterprise profitability by GARCH-Mmodel and calculate the credit default distance of enterprise by KMV model. Throughmodified KMV model we calculate the occurrence rate of credit default. Then we can usecopula connect dependent structure to measure the market default probability in thesupply chain.
In chapter6by the confirmatory factor analysis (CFA) of the structural equation(SEM) we check the structural model of financial risk and get out to what extentindicator variables can explain the potential variables through factor loading from ourmodel. By second-order CFA, we find out to what extent the first-order potentialvariables will affect the financial risk and to what degree the potential variables dependon each other and the validity of the combination of the whole model.
In chapter7we build up risk warning system, correct the ranking results of financialand credit risk of enterprise financing by circularly revised combination evaluation model,and get the ranking results of enterprise financing risk based on supply chain, then wecan build up colored risk level warning. Finally by CFA we build up enterprise financing risk indicator identifying system.
Our main innovation:1. construct the relational structure among the enterprises byArchimedes copula function;2. measure the financing risk of the supply chain financingby the information entropy and copula connect structure;3. estimate earnings volatilityby GARCH-M model, combine KMV model and copulas connect structure to measurecredit risk of supply chain financing;4. analyze the influence factors of supply chainfinancing by SEM theory5. constantly correct the results of supply chain financing bycircularly revised combination evaluation model.
引文
①刘艳春．一组循环修正的组合评价方法[J]．数学的实践与认识，2007，37（4）：88-94
[1] Alen N Berger,Gregory F Udell.A More Complete Conceptual Framework for SMEFinance[R].World Bank Conference on Small and Medium Enterprises: OvercomingGrowth Constraints,MC13-121,October,2004,14-15
[2] Chen, H., Amodeo,L.,Chu, F., Labadi, K.. Modeling and Performance Evaluation ofSupply Chains Using Batch Deterministic and Stochastic Petri Nets[J].IEEETransactions on Automation Science and Engineering,2005,2(2):132-144
[3] Claes M, Cassel PH, Anders HW. On measurement of intangible asset: A study ofrobustness of partial least squares[J]. Total Quality Management&BusinessExcellence,2000,11(7):897
[4] David Gustin.Emerging Trends in supply chain finance[J].WORD TRADE,2005(8),52-53
[5] Demarta, S., McNeil, A.J., The t-copula and related copulas[J]. InternationalStatistical Review,2005,73:111-129
[6] Embrechts,P., A.McNeil and D. Straumann.Correlation and dependence in riskManagement:properties and pitfalls [J].Risk management: value at risk and beyond,2002:176-223
[7] Embrechts, P., H ing, A., Juri A. Using Copulae to bound the Value-at-Risk forfunctions of dependent risks[J]. Finance&Stochastics,2003,7:145-167
[8] Embreehts P, Lindskog F,A,M.. Modelling Dependence with Copulas andApplications to Risk Management. Working Paper.2003
[9] Engle, R. F., Dynamic conditional correlation: A simple class of multivariategeneralized autoregressive conditional heteroskedasticity models[J]. Journal ofBusiness and Economic Statistics,2002,20:339-350
[10] Everitt,B.,Dunn,G.. Applied Multivariate Data Analysis[M]. New York: Oxford,2001
[11] Fang Ping,Xiong Ruiqing. The applying of structural equation modeling in theresearch of psychology[J].Psychology Science,2001,24(4):406-408
[12] Gaonkar, R.s., Viswanadham, N.. Analytical framework for the management of riskin supply chains[J]. IEEE Transactions on Automation Science and Engineering,2007,4(2):1265-1273
[13] Gilberto Miller Devos Ganga.A fuzzy logic approach to supply chain performancemanagement[J]. Int.J.Production Economics,2011,134:177-187
[14] Giacomini, E., Hardle, W., Spokoiny, Inhomogeneous dependence modeling withtime-varying copula[J]. Journal of Business and Economic Statistics,2009,27(2):224-234
[15] Gonzalo Guillen,Mariana Badell. A holistic framework for short-term supply chainmanagement integrating production and corporate financial planning[J].ProductionEconomics,2006(7):25-27
[16] Gregor N. F. Wei. Copula-GARCH versus dynamic conditional correlation:anempirical study on VaR and ES forecasting accuracy. Rev Quant Finan Acc (2013)41:179–202.DOI10.1007/s11156-012-0311-2
[17] Hafner, C. M., Reznikova, O. Efficient estimation of a semiparametric dynamiccopula model[R]. Manuscript, Institute of Statistics, UCL,2008
[18] H rdle, W., R. A. Moro and D. Sch fer. Estimating probabilities of default withsupport vector machines [M], Citeseer,2007
[19] He, X. and P. Gong. Measuring the coupled risks: A copula-based CVaR model [J].Journal of Computational and Applied Mathematics,2009,223(2):1066-1080
[20] Huiyong WU,Yanchun LIU. The Supply Chain Model of Finance Payment, WhichMade up of Providers, Central Enterprises and Distributors[J]. InformationTechnology Journal,2013,12(18):4699-4704,DOI:10.3923/itj.2013.4699.4704
[21] Jondeau, E., Rockinger, M. The copula-garch model of conditional dependencies:An international stock market application[J]. Journal of International Money andFinance,2006,25:827-853
[22] Khashman, A. Neural networks for credit risk evaluation: Investigation of differentneural models and learning schemes [J]. Expert Systems with Applications,2010,37(9):6233-6239
[23] Kim, H. S. and S. Y. Sohn. Support vector machines for default prediction of SMEsbased on technology credit [J]. European journal of operational research,2010,201(3):838-846
[24] Leora Mapper. The Role of “Reverse Factoring”in Supplier Financing of Small andMedium Sized Enterprises[R].World Bank, September,2004,102-103
[25] Malgorzata Doman, Dynamic linkages between stock markets: the effects of crisesand globalization[J], Port Econ J,2013,12:87–112,DOI10.1007/s10258-013-0091-1.
[26] Martin D. Early Warnings of Bank Failure: A Logit Regression Approach[J].Journalof Banking and Finance,1977(1):249-276
[27] McNeil, A.J., Frey, R., Embrechts, P.,Quantitative Risk Management:Concepts,Techniques and Tools[M]. Princeton University Press, New Jersey,2005
[28] McNeil, A. J. Sampling nested Archimedean copulas[J]. Journal of StatisticalComputation and Simulation,2008,78(6):567-581
[29] Miehael Lamoureux. A Supply Chain Finance Prime. http://www. esoureingwiki.com/index.phn/A_Supply_chain-Financejrimer,2008
[30] N.R.Srinivasa Raghavan. Short-term financing in a cash-constrained supply chain[J].nt.J. Production Economics,2011,134:407-412
[31] Nagurney A, Cruz J, Dong J, Ding Zhang. Supply chain networks, electroniccommerce and supply side and demand side risk[J]. European Journal of OperationalResearch,2004(64):120-142
[32] Ohlson J.A. Financial Ratios and Probabilistic Prediction of Bankruptcy [J].Journalof Accounting Research,1980(18):109-131
[33] Patton, A. J. On the out-of-sample importance of skewness and asymmetricdependence for asset allocation[J]. Journal of Financial Econometrics,2004,2(1):130-168
[34] Patton, A. J. Estimation of multivariate models for time series of possibly differentlengths [J]. Journal of Applied Econometrics,2006a,21(2):147-173
[35] Patton, A. J. Modelling asymmetric exchange rate dependence [J]. InternationalEconomic Review,2006b,47(2):527-556
[36] Patton, A. J., Copula-Based Models for Financial Time Series[R]. OFRC WorkingPapers Series2008fe21, Oxford Financial Research Centre,2008
[37] Robert I.Kabacoff. R语言实战[M].北京:人民邮电出版社,2013
[38] Rodriguez, J. C. Measuring financial contagion: a copula approach[J]. Journal ofEmpirical Finance,2007,14(3):401-423
[39] Romano, C., Applying copula function to risk management[R]. Rome:University ofRome, La Sapienza,2002
[40] Rosenberg, J. V., A general approach to integrated risk management with skewed,fat-tailed risks[J]. Journal of Financial Economics,2006,79,569-614
[41] Rudiger Kiesel. A Multivariate Commodity Analysis with Time-DependentVolatility—Evidence from the German Energy Market[J]. Z Energiewirtsch,2013,37:107–126DOI10.1007/s12398-012-0102-4
[42] Spicer,J.. Making Sense of Multivariate Data Analysis[M]. London: Sage,2005
[43] Sushil Gupta. Production, Manufacturing and Logistics Modeling of financialsupply chain[J].European Journal of Operational Research,2011,211:47-56
[44] Sustersic, M., D. Mramor and J. Zupan. Consumer credit scoring models withlimited data [J]. Expert Systems with Applications,2009,36(3):4736-4744
[45] Tang, D. Y. and H. Yan. Market conditions, default risk and credit spreads [J].Journal of Banking&Finance,2010,34(4):743-753
[46] Tomasz R. Bielecki. Dynamic Hedging of Portfolio Credit Risk in a Markov CopulaModel,J Optim Theory Appl, DOI10.1007/s10957-013-0318-4
[47] Vinzi V E, Tenenhaus M. PLS Logistic Regression[M].2002
[48] Yu, L., W. Yue, S. Wang, et al. Support vector machine based multiagent ensemblelearning for credit risk evaluation [J]. Expert Systems with Applications,2010,37(2):1351-1360
[49] Zhihui Gu, Endogenous default risk in supply chain and non-linear pricing[J]. Int.J.Production Economics,2012,139:90-96
[50] Zolkos, Rodd. Attention to supply-chain risks grows[J]. Bussiness Insurance,2003(37):17-29
[51]陈祥锋，朱道立和应雯珺．资金约束与供应链中的融资和运营综合决策研究[J]．管理科学学报，2008（3）：70-77
[52]陈祥锋，朱道立．现代物流金融服务创新——金融物流[J]．物流技术，2005（3）：4-6
[53]陈祥锋．供应链服务创新论[M]．上海：复旦大学出版社，2008
[54]陈祥锋．融通仓与物流金融服务创新[J]．科技导报，2005（9）：30-33
[55]邓艳芳，童恒庆．基于结构方程模型的风险投资的风险因素分析[J]．武汉理工大学学报，2008，30（2）：312-315
[56]方福前，吕文惠．中国城镇居民福利水平影响因素分析——基于阿马蒂亚森的能力方法和结构方程模型[J]．管理世界，2009（4）：17-25
[57]高文杰，高旭．基于SEM的我国重要城市现代化水平综合评价模型研究[J]．数学的实践与认识，2010．9，第40卷第18期，56-64
[58]郭晴．供应链金融模式分类及风险研究[D]．博士学位论文，天津大学，2011
[59]郭涛．中小企业融资的新渠道[J]．经济师，2005（2）：152-153
[60]何志慧．供应链金融及其风险管理[D]．博士学位论文，华东师范大学，2011
[61]李碧珍．融通仓：中小企业融资新思路[J]．商讯商业经济文荟，2005（3）：86-88
[62]李建平．风险相关性下的信用风险、市场风险和操作风险集成度量[J]．中国管理科学，2010（1）：18-25
[63]李秀敏，史道济．金融市场组合风险的相关性研究[J]．系统工程理论与实践，2007（2）:112-117
[64]李毅学．供应链金融风险评估[J]．中央财经大学学报，2011（10）：36-41
[65]李志辉，罗平．PASW/SPSS Statistics中文版统计分析教程[M]．北京：电子工业出版社，2010
[66]梁琪．企业经营管理预警：主成分分析在logistic回归方法中的应用[J]．管理工程学报，19（1）：100-103
[67]林盛，刘金兰，韩文秀．基于PLS-结构方程的顾客满意度评价方法[J]．系统工程学报，2005，20（6）：653-656
[68]刘艳春．一组循环修正的组合评价方法[J]．数学的实践与认识，2007，37（4）：88-94
[69]刘永胜．供应链风险研究[M]．北京：知识产权出版社，2011
[70]柳超．基于相依违约的企业集团信用风险度量研究[D]．博士学位论文，中南大学，2008
[71]鲁迅法．Copula方法在金融风险管理中的应用[D]．博士学位论文，中国科学技术大学，2012
[72]马佳．供应链金融融资模式分析及风险控制[D]．博士学位论文，天津大学，2008．
[73]马士华，林勇．供应链管理[M]．北京：高等教育出版社，2003
[74]邱昊．延期支付条件下的最优付款时间的确定：考虑现金折扣情形[J]．管理学报，2007，4（2）：191-200
[75]任仙玲，张世英．基于核估计及多元阿基米德Copula的投资组合风险分析[J]．管理科学，2007（5）：92-97
[76]任仙玲，张世英．基于Copula函数的金融市场尾部相关性分析[J]．统计与信息论坛，2008（6）：66-71
[77]任仙玲，张世英．基于Copula函数的金融市场尾部相关性分析[J]，统计与信息论坛，2008，23（6）：66-71
[78]深圳发展银行，中欧国际商学院．供应链金融[M]．上海：上海远东出版社，2009
[79]唐少艺．物流金融实务研究[J]．中国物流与采购，2005（2）：45-48
[80]田飞．用结构方程模型建构指标体系[J]．安徽大学学报，2007，31（6）：92-95
[81]王惠文．偏最小二乘回归的线性与非线性方法[M]．北京：国防工业出版社，2006
[82]王苗雯．供应链金融中企业组合信用风险度量问题研究[D]．博士学位论文，上海师范大学，2012
[83]王霄，胡军．社会资本结构与中小企业创新——基于结构方程模型的实证研究[J]．管理世界，2005（7）：116-121
[84]王小宁．基于违约相依的信用风险度量与传染效应研究[D]．博士学位论文，中南大学，2010
[85]王周伟，王苗雯．美国金融危机初始因素的敏感性分析——基于KMV模型[J]．统计与信息论坛，2010（1）：73-78
[86]韦艳华，张世英，郭焱．金融市场相关程度与相关模式的研究[J]．系统工程学报，2004，19（4）：355-362
[87]韦艳华，张世英．Copula理论在金融上的应用[J]．西北农林科技大学学报（社会科学版），2003（5）：97-101
[88]韦艳华，张世英．金融市场的相关性分析——Copula-GARCH模型及其应用[J]．系统工程，2004（4）：7-12
[89]韦艳华，张世英．金融市场动态相关结构的研究[J]系统工程学报，2006，21（3）：313-317
[90]吴兵福．结构方程模型初步研究[D]．博士学位论文，天津大学，2006
[91]吴明隆．结构方程模型——AMOS的操作与应用[M]．重庆：重庆大学出版社，2012
[92]徐海超．供应链核心企业的金融服务风险评价研究——以制造业为例[D]．博士学位论文，南昌大学，2012．
[93]闫俊宏，许祥秦．基于供应链金融的中小企业融资模式分析[J]．上海金融，2007（2）：14-16
[94]杨绍辉．从商业银行的业务模式看供应链融资服务[J]．物流技术，2005（10）：180-182
[95]叶五一，缪柏其，吴振翔．基于Copula方法的条件VaR估计[J]．中国科学技术大学学报2006，36（9）：917-922
[96]叶五一，缪柏其．基于Copula变点检测的美国次级债金融危机传染分析[J]．中国管理科学2009，17（3）：1-7
[97]于立勇，詹捷辉．基于Logistic回归分析的违约概率预测研究[J]．财经研究，2004（9）：15-23
[98]于瑞峰．基于供应链的企业信贷风险评估研究[J]．中国管理科学，2007（3）：85-92
[99]张传新，王光伟．基于主成分分析和Logit模型的商业银行信用风险度量研究[J]．西部经济管理论坛，2012（4）：17-23
[100]张琅．供应链金融信用风险评估研究[D]．博士学位论文，西安理工大学，2010
[101]张玮．供应链金融风险识别及信用风险度量[D]．博士学位论文，大连海事大学，2010
[102]张晓建．供应链中的批量与信用期联合决策研究[J]．中国管理学，2011，19（5）：42-49
[103]张尧庭．连接函数（Copula）技术与金融风险分析[J]．统计研究，2002（4）：48-51
[104]张尧庭．我们应该选用什么样的相关性指标[J]．统计研究，2002（9）：41-44
[105]赵丽琴．基于Copula函数的金融风险度量研究[D]．博士学位论文，厦门大学，2009
[106]郑立群，陈伟伟，张宇．区域低碳发展影响因素的结构方程模型分析[J]．河南科学，2013，31（1）：108-112
[1] Alen N Berger,Gregory F Udell.A More Complete Conceptual Framework for SMEFinance[R].World Bank Conference on Small and Medium Enterprises: OvercomingGrowth Constraints,MC13-121,October,2004,14-15
[2] Chen, H., Amodeo,L.,Chu, F., Labadi, K.. Modeling and Performance Evaluation ofSupply Chains Using Batch Deterministic and Stochastic Petri Nets[J].IEEETransactions on Automation Science and Engineering,2005,2(2):132-144
[3] Claes M, Cassel PH, Anders HW. On measurement of intangible asset: A study ofrobustness of partial least squares[J]. Total Quality Management&BusinessExcellence,2000,11(7):897
[4] David Gustin.Emerging Trends in supply chain finance[J].WORD TRADE,2005(8),52-53
[5] Demarta, S., McNeil, A.J., The t-copula and related copulas[J]. InternationalStatistical Review,2005,73:111-129
[6] Embrechts,P., A.McNeil and D. Straumann.Correlation and dependence in riskManagement:properties and pitfalls [J].Risk management: value at risk and beyond,2002:176-223
[7] Embrechts, P., H ing, A., Juri A. Using Copulae to bound the Value-at-Risk forfunctions of dependent risks[J]. Finance&Stochastics,2003,7:145-167
[8] Embreehts P, Lindskog F,A,M.. Modelling Dependence with Copulas andApplications to Risk Management. Working Paper.2003
[9] Engle, R. F., Dynamic conditional correlation: A simple class of multivariategeneralized autoregressive conditional heteroskedasticity models[J]. Journal ofBusiness and Economic Statistics,2002,20:339-350
[10] Everitt,B.,Dunn,G.. Applied Multivariate Data Analysis[M]. New York: Oxford,2001
[11] Fang Ping,Xiong Ruiqing. The applying of structural equation modeling in theresearch of psychology[J].Psychology Science,2001,24(4):406-408
[12] Gaonkar, R.s., Viswanadham, N.. Analytical framework for the management of riskin supply chains[J]. IEEE Transactions on Automation Science and Engineering,2007,4(2):1265-1273
[13] Gilberto Miller Devos Ganga.A fuzzy logic approach to supply chain performancemanagement[J]. Int.J.Production Economics,2011,134:177-187
[14] Giacomini, E., Hardle, W., Spokoiny, Inhomogeneous dependence modeling withtime-varying copula[J]. Journal of Business and Economic Statistics,2009,27(2):224-234
[15] Gonzalo Guillen,Mariana Badell. A holistic framework for short-term supply chainmanagement integrating production and corporate financial planning[J].ProductionEconomics,2006(7):25-27
[16] Gregor N. F. Wei. Copula-GARCH versus dynamic conditional correlation:anempirical study on VaR and ES forecasting accuracy. Rev Quant Finan Acc (2013)41:179–202.DOI10.1007/s11156-012-0311-2
[17] Hafner, C. M., Reznikova, O. Efficient estimation of a semiparametric dynamiccopula model[R]. Manuscript, Institute of Statistics, UCL,2008
[18] H rdle, W., R. A. Moro and D. Sch fer. Estimating probabilities of default withsupport vector machines [M], Citeseer,2007
[19] He, X. and P. Gong. Measuring the coupled risks: A copula-based CVaR model [J].Journal of Computational and Applied Mathematics,2009,223(2):1066-1080
[20] Huiyong WU,Yanchun LIU. The Supply Chain Model of Finance Payment, WhichMade up of Providers, Central Enterprises and Distributors[J]. InformationTechnology Journal,2013,12(18):4699-4704,DOI:10.3923/itj.2013.4699.4704
[21] Jondeau, E., Rockinger, M. The copula-garch model of conditional dependencies:An international stock market application[J]. Journal of International Money andFinance,2006,25:827-853
[22] Khashman, A. Neural networks for credit risk evaluation: Investigation of differentneural models and learning schemes [J]. Expert Systems with Applications,2010,37(9):6233-6239
[23] Kim, H. S. and S. Y. Sohn. Support vector machines for default prediction of SMEsbased on technology credit [J]. European journal of operational research,2010,201(3):838-846
[24] Leora Mapper. The Role of “Reverse Factoring”in Supplier Financing of Small andMedium Sized Enterprises[R].World Bank, September,2004,102-103
[25] Malgorzata Doman, Dynamic linkages between stock markets: the effects of crisesand globalization[J], Port Econ J,2013,12:87–112,DOI10.1007/s10258-013-0091-1.
[26] Martin D. Early Warnings of Bank Failure: A Logit Regression Approach[J].Journalof Banking and Finance,1977(1):249-276
[27] McNeil, A.J., Frey, R., Embrechts, P.,Quantitative Risk Management:Concepts,Techniques and Tools[M]. Princeton University Press, New Jersey,2005
[28] McNeil, A. J. Sampling nested Archimedean copulas[J]. Journal of StatisticalComputation and Simulation,2008,78(6):567-581
[29] Miehael Lamoureux. A Supply Chain Finance Prime. http://www. esoureingwiki.com/index.phn/A_Supply_chain-Financejrimer,2008
[30] N.R.Srinivasa Raghavan. Short-term financing in a cash-constrained supply chain[J].nt.J. Production Economics,2011,134:407-412
[31] Nagurney A, Cruz J, Dong J, Ding Zhang. Supply chain networks, electroniccommerce and supply side and demand side risk[J]. European Journal of OperationalResearch,2004(64):120-142
[32] Ohlson J.A. Financial Ratios and Probabilistic Prediction of Bankruptcy [J].Journalof Accounting Research,1980(18):109-131
[33] Patton, A. J. On the out-of-sample importance of skewness and asymmetricdependence for asset allocation[J]. Journal of Financial Econometrics,2004,2(1):130-168
[34] Patton, A. J. Estimation of multivariate models for time series of possibly differentlengths [J]. Journal of Applied Econometrics,2006a,21(2):147-173
[35] Patton, A. J. Modelling asymmetric exchange rate dependence [J]. InternationalEconomic Review,2006b,47(2):527-556
[36] Patton, A. J., Copula-Based Models for Financial Time Series[R]. OFRC WorkingPapers Series2008fe21, Oxford Financial Research Centre,2008
[37] Robert I.Kabacoff. R语言实战[M].北京:人民邮电出版社,2013
[38] Rodriguez, J. C. Measuring financial contagion: a copula approach[J]. Journal ofEmpirical Finance,2007,14(3):401-423
[39] Romano, C., Applying copula function to risk management[R]. Rome:University ofRome, La Sapienza,2002
[40] Rosenberg, J. V., A general approach to integrated risk management with skewed,fat-tailed risks[J]. Journal of Financial Economics,2006,79,569-614
[41] Rudiger Kiesel. A Multivariate Commodity Analysis with Time-DependentVolatility—Evidence from the German Energy Market[J]. Z Energiewirtsch,2013,37:107–126DOI10.1007/s12398-012-0102-4
[42] Spicer,J.. Making Sense of Multivariate Data Analysis[M]. London: Sage,2005
[43] Sushil Gupta. Production, Manufacturing and Logistics Modeling of financialsupply chain[J].European Journal of Operational Research,2011,211:47-56
[44] Sustersic, M., D. Mramor and J. Zupan. Consumer credit scoring models withlimited data [J]. Expert Systems with Applications,2009,36(3):4736-4744
[45] Tang, D. Y. and H. Yan. Market conditions, default risk and credit spreads [J].Journal of Banking&Finance,2010,34(4):743-753
[46] Tomasz R. Bielecki. Dynamic Hedging of Portfolio Credit Risk in a Markov CopulaModel,J Optim Theory Appl, DOI10.1007/s10957-013-0318-4
[47] Vinzi V E, Tenenhaus M. PLS Logistic Regression[M].2002
[48] Yu, L., W. Yue, S. Wang, et al. Support vector machine based multiagent ensemblelearning for credit risk evaluation [J]. Expert Systems with Applications,2010,37(2):1351-1360
[49] Zhihui Gu, Endogenous default risk in supply chain and non-linear pricing[J]. Int.J.Production Economics,2012,139:90-96
[50] Zolkos, Rodd. Attention to supply-chain risks grows[J]. Bussiness Insurance,2003(37):17-29
[51]陈祥锋，朱道立和应雯珺．资金约束与供应链中的融资和运营综合决策研究[J]．管理科学学报，2008（3）：70-77
[52]陈祥锋，朱道立．现代物流金融服务创新——金融物流[J]．物流技术，2005（3）：4-6
[53]陈祥锋．供应链服务创新论[M]．上海：复旦大学出版社，2008
[54]陈祥锋．融通仓与物流金融服务创新[J]．科技导报，2005（9）：30-33
[55]邓艳芳，童恒庆．基于结构方程模型的风险投资的风险因素分析[J]．武汉理工大学学报，2008，30（2）：312-315
[56]方福前，吕文惠．中国城镇居民福利水平影响因素分析——基于阿马蒂亚森的能力方法和结构方程模型[J]．管理世界，2009（4）：17-25
[57]高文杰，高旭．基于SEM的我国重要城市现代化水平综合评价模型研究[J]．数学的实践与认识，2010．9，第40卷第18期，56-64
[58]郭晴．供应链金融模式分类及风险研究[D]．博士学位论文，天津大学，2011
[59]郭涛．中小企业融资的新渠道[J]．经济师，2005（2）：152-153
[60]何志慧．供应链金融及其风险管理[D]．博士学位论文，华东师范大学，2011
[61]李碧珍．融通仓：中小企业融资新思路[J]．商讯商业经济文荟，2005（3）：86-88
[62]李建平．风险相关性下的信用风险、市场风险和操作风险集成度量[J]．中国管理科学，2010（1）：18-25
[63]李秀敏，史道济．金融市场组合风险的相关性研究[J]．系统工程理论与实践，2007（2）:112-117
[64]李毅学．供应链金融风险评估[J]．中央财经大学学报，2011（10）：36-41
[65]李志辉，罗平．PASW/SPSS Statistics中文版统计分析教程[M]．北京：电子工业出版社，2010
[66]梁琪．企业经营管理预警：主成分分析在logistic回归方法中的应用[J]．管理工程学报，19（1）：100-103
[67]林盛，刘金兰，韩文秀．基于PLS-结构方程的顾客满意度评价方法[J]．系统工程学报，2005，20（6）：653-656
[68]刘艳春．一组循环修正的组合评价方法[J]．数学的实践与认识，2007，37（4）：88-94
[69]刘永胜．供应链风险研究[M]．北京：知识产权出版社，2011
[70]柳超．基于相依违约的企业集团信用风险度量研究[D]．博士学位论文，中南大学，2008
[71]鲁迅法．Copula方法在金融风险管理中的应用[D]．博士学位论文，中国科学技术大学，2012
[72]马佳．供应链金融融资模式分析及风险控制[D]．博士学位论文，天津大学，2008．
[73]马士华，林勇．供应链管理[M]．北京：高等教育出版社，2003
[74]邱昊．延期支付条件下的最优付款时间的确定：考虑现金折扣情形[J]．管理学报，2007，4（2）：191-200
[75]任仙玲，张世英．基于核估计及多元阿基米德Copula的投资组合风险分析[J]．管理科学，2007（5）：92-97
[76]任仙玲，张世英．基于Copula函数的金融市场尾部相关性分析[J]．统计与信息论坛，2008（6）：66-71
[77]任仙玲，张世英．基于Copula函数的金融市场尾部相关性分析[J]，统计与信息论坛，2008，23（6）：66-71
[78]深圳发展银行，中欧国际商学院．供应链金融[M]．上海：上海远东出版社，2009
[79]唐少艺．物流金融实务研究[J]．中国物流与采购，2005（2）：45-48
[80]田飞．用结构方程模型建构指标体系[J]．安徽大学学报，2007，31（6）：92-95
[81]王惠文．偏最小二乘回归的线性与非线性方法[M]．北京：国防工业出版社，2006
[82]王苗雯．供应链金融中企业组合信用风险度量问题研究[D]．博士学位论文，上海师范大学，2012
[83]王霄，胡军．社会资本结构与中小企业创新——基于结构方程模型的实证研究[J]．管理世界，2005（7）：116-121
[84]王小宁．基于违约相依的信用风险度量与传染效应研究[D]．博士学位论文，中南大学，2010
[85]王周伟，王苗雯．美国金融危机初始因素的敏感性分析——基于KMV模型[J]．统计与信息论坛，2010（1）：73-78
[86]韦艳华，张世英，郭焱．金融市场相关程度与相关模式的研究[J]．系统工程学报，2004，19（4）：355-362
[87]韦艳华，张世英．Copula理论在金融上的应用[J]．西北农林科技大学学报（社会科学版），2003（5）：97-101
[88]韦艳华，张世英．金融市场的相关性分析——Copula-GARCH模型及其应用[J]．系统工程，2004（4）：7-12
[89]韦艳华，张世英．金融市场动态相关结构的研究[J]系统工程学报，2006，21（3）：313-317
[90]吴兵福．结构方程模型初步研究[D]．博士学位论文，天津大学，2006
[91]吴明隆．结构方程模型——AMOS的操作与应用[M]．重庆：重庆大学出版社，2012
[92]徐海超．供应链核心企业的金融服务风险评价研究——以制造业为例[D]．博士学位论文，南昌大学，2012．
[93]闫俊宏，许祥秦．基于供应链金融的中小企业融资模式分析[J]．上海金融，2007（2）：14-16
[94]杨绍辉．从商业银行的业务模式看供应链融资服务[J]．物流技术，2005（10）：180-182
[95]叶五一，缪柏其，吴振翔．基于Copula方法的条件VaR估计[J]．中国科学技术大学学报2006，36（9）：917-922
[96]叶五一，缪柏其．基于Copula变点检测的美国次级债金融危机传染分析[J]．中国管理科学2009，17（3）：1-7
[97]于立勇，詹捷辉．基于Logistic回归分析的违约概率预测研究[J]．财经研究，2004（9）：15-23
[98]于瑞峰．基于供应链的企业信贷风险评估研究[J]．中国管理科学，2007（3）：85-92
[99]张传新，王光伟．基于主成分分析和Logit模型的商业银行信用风险度量研究[J]．西部经济管理论坛，2012（4）：17-23
[100]张琅．供应链金融信用风险评估研究[D]．博士学位论文，西安理工大学，2010
[101]张玮．供应链金融风险识别及信用风险度量[D]．博士学位论文，大连海事大学，2010
[102]张晓建．供应链中的批量与信用期联合决策研究[J]．中国管理学，2011，19（5）：42-49
[103]张尧庭．连接函数（Copula）技术与金融风险分析[J]．统计研究，2002（4）：48-51
[104]张尧庭．我们应该选用什么样的相关性指标[J]．统计研究，2002（9）：41-44
[105]赵丽琴．基于Copula函数的金融风险度量研究[D]．博士学位论文，厦门大学，2009
[106]郑立群，陈伟伟，张宇．区域低碳发展影响因素的结构方程模型分析[J]．河南科学，2013，31（1）：108-112